Development of phenotype algorithms using electronic medical records and incorporating natural language processing.

Journal: BMJ (Clinical research ed.)
Published Date: Apr 24, 2015

Abstract

Electronic medical records are emerging as a major source of data for clinical and translational research studies, although phenotypes of interest need to be accurately defined first. This article provides an overview of how to develop a phenotype algorithm from electronic medical records, incorporating modern informatics and biostatistics methods.

Authors

  • Katherine P Liao
    Department of Biomedical Informatics, Harvard Medical School, Boston, MA, United States.
  • Tianxi Cai
    Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, United States.
  • Guergana K Savova
    Department of Pediatrics, Children's Hospital of Boston, Boston.
  • Shawn N Murphy
  • Elizabeth W Karlson
    Division of Rheumatology, Immunology and Allergy, Brigham and Women's Hospital, Boston, MA 02115, USA Harvard Medical School, Boston.
  • Ashwin N Ananthakrishnan
    Department of Gastroenterology, Massachusetts General Hospital, MGH Crohn's and Colitis Center, Boston.
  • Vivian S Gainer
    Research Computing, Partners HealthCare, Charlestown, MA, USA.
  • Stanley Y Shaw
    Massachusetts General Hospital, Boston, MA.
  • Zongqi Xia
    Department of Neurology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA.
  • Peter Szolovits
    Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA.
  • Susanne Churchill
    Harvard Medical School, Boston.
  • Isaac Kohane
    Harvard Medical School, Boston Department of Neurology, Massachusetts General Hospital, Boston.

Keywords

External Resources

Popular Topics
Recent Journals